© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 17330
    Prev
    Next
    INDEX
    Explanations

    prosecution-related terms, such as names of suspects, criminal charges, and legal actions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "of" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    attribute
    -0.78
     entit
    -0.70
    obyl
    -0.65
    TEXT
    -0.65
    âĢķ
    -0.64
     surrog
    -0.64
     disse
    -0.63
    Characters
    -0.63
     compiled
    -0.63
     substr
    -0.62
    POSITIVE LOGITS
     Pasadena
    0.98
     Queens
    0.92
     Oakland
    0.90
     Auckland
    0.87
     Antioch
    0.86
     Anaheim
    0.86
     Providence
    0.86
     Minneapolis
    0.84
     Brooklyn
    0.83
     Rochester
    0.83
    Activations Density 0.056%

    No Known Activations